gliclass-v4:2b
3 TagsUpdated 2.4B params8192 contextEnglishApache-2.0by Knowledgator
gliclass-v4-2b (decoder-KV on Qwen3.5-2B, 2.4B weights read), fp32 compute on BF16 weights: about 7 GB in memory.
2.4b
ollaya run gliclass-v4:2b --preset triage "I was charged twice for my subscription this month and want a refund."curl http://localhost:11435/api/decide \
-H "Content-Type: application/json" \
-d '{
"model": "gliclass-v4:2b",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
}'# Already using a TypeSafe SDK? Set TYPESAFE_BASE_URL=http://localhost:11435 instead.
import requests
response = requests.post(
"http://localhost:11435/api/decide",
json={
"model": "gliclass-v4:2b",
"state": "I was charged twice for my subscription this month and want a refund.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Payments, invoices and refunds",
"technical": "Bugs, errors and outages",
"account": "Login, profile and settings"
}
},
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
},
)
answers = response.json()["answers"]
print(answers["department"]["choice"], answers["refund"]["noul"])const response = await fetch("http://localhost:11435/api/decide", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model: "gliclass-v4:2b",
state: "I was charged twice for my subscription this month and want a refund.",
questions: {
department: {
type: "choice",
instructions: "Which team should handle this?",
criteria: {
billing: "Payments, invoices and refunds",
technical: "Bugs, errors and outages",
account: "Login, profile and settings"
}
},
refund: {
type: "noul",
instructions: "Is the customer asking for a refund?"
}
}
}),
});
const { answers } = await response.json();
console.log(answers.department.choice, answers.refund.noul);Details
- graphcce70796f1a8 · 12 MB
onnx · gliclass-kv · 2.4B · fp32 - weights8b8308376488 · 4.7 GB
huggingface.co/knowledgator/gliclass-v4-2b/resolve/40fe023…/model.safetensors - tokenizer04472e9fcd4a · 20 MB
huggingface.co/knowledgator/gliclass-v4-2b/resolve/40fe023…/tokenizer.json - decision422d5d5104c9 · 3 KB
{"engine": "onnx", "family": "gliclass-kv", "encoder": "", "layout": "gliclass-kv-v1", …} - calibrationadff5b1a2745 · 177 B
{"temperature": [1.0, 1.0, 1.0]} - license94fbb5a513de · 10 KB
GLiClass v4 by Knowledgator (https://huggingface.co/knowledgator/gliclass-v4-2b, https://huggingface.co/knowledgator/gliclass-v4-9b)
Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.